<?xml-model href='http://www.tei-c.org/release/xml/tei/custom/schema/relaxng/tei_all.rng' schematypens='http://relaxng.org/ns/structure/1.0'?><TEI xmlns="http://www.tei-c.org/ns/1.0">
	<teiHeader>
		<fileDesc>
			<titleStmt><title level='a'>Repurposing Entailment for Multi-Hop Question Answering Tasks</title></titleStmt>
			<publicationStmt>
				<publisher></publisher>
				<date>2019 June</date>
			</publicationStmt>
			<sourceDesc>
				<bibl> 
					<idno type="par_id">10098274</idno>
					<idno type="doi"></idno>
					<title level='j'>North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
<idno></idno>
<biblScope unit="volume">1</biblScope>
<biblScope unit="issue"></biblScope>					

					<author>Harsh Trivedi</author><author>Heeyoung Kwon</author><author>Tushar Khot</author><author>Ashish Sabharwal</author><author>Niranjan Balasubramanian</author>
				</bibl>
			</sourceDesc>
		</fileDesc>
		<profileDesc>
			<abstract><ab><![CDATA[Question Answering (QA) naturally reduces to an entailment problem, namely, verifying whether some text entails the answer to a question. However, for multi-hop QA tasks, which require reasoning with \textit{multiple} sentences, it remains unclear how best to utilize entailment models pre-trained on large scale datasets such as SNLI, which are based on sentence pairs. We introduce Multee, a general architecture that can effectively use entailment models for multi-hop QA tasks. Multee uses (i) a local module that helps locate important sentences, thereby avoiding distracting information, and (ii) a global module that aggregates information by effectively incorporating importance weights. Importantly, we show that both modules can use entailment functions pre-trained on a large scale NLI datasets. We evaluate performance on MultiRC and OpenBookQA, two multihop QA datasets. When using an entailment function pre-trained on NLI datasets, Multee outperforms QA models trained only on the target QA datasets and the OpenAI transformer models.]]></ab></abstract>
		</profileDesc>
	</teiHeader>
	<text><body><div/></body></text>
</TEI>
